JP7706320B2 - Computer, robot control method, and computer system - Google Patents

Description

The present invention relates to the control of a robot that performs tasks including grasping and moving an object.

The technology described in Patent Document 1 is known as a technology for controlling a robot that performs tasks including grasping objects and moving items. Patent Document 1 describes a control device that "includes a state information generation unit that generates and updates state information regarding the robot and the grasped object, and a control information generation unit that generates control information for controlling the robot based on a pre-generated base trajectory along which the robot can move the grasped object from a start point to an end point, and the state information."

JP 2021-84159 A JP 2019-942 A

In the technology described in Patent Document 1, control is performed based on the current state. By taking future states into account, it is expected that more accurate robot control can be achieved. The object of the present invention is to realize a system and method that can control a robot with greater accuracy.

A representative example of the invention disclosed in the present application is as follows: That is, a computer for controlling a robot performing a task including grasping and moving an object includes an arithmetic unit, a storage device connected to the arithmetic unit, and an interface connected to the arithmetic unit, the storage device holds trajectory information related to a trajectory of the robot when grasping and moving the object during the task of the robot, the arithmetic unit acquires first operating status information including a value indicating an operating status of the robot during the task and work status information including a value for grasping the state of the object grasped by the robot, generates second operating status information including a value indicating a future operating status of the robot during the task generated based on the trajectory information, and estimated work status information including a value for grasping the future state of the object grasped by the robot based on the first operating status information and the work status information, and generates control information for controlling the robot based on the trajectory information, the first operating status information, the work status information, and the estimated work status information.

The present invention allows robots to be controlled with high precision. Problems, configurations, and advantages other than those described above will become clear from the description of the embodiments below.

FIG. 1 illustrates an example of a system configuration according to a first embodiment. FIG. 2 is a diagram illustrating an example of a data structure of robot configuration information according to the first embodiment. FIG. 4 is a diagram illustrating an example of a data structure of facility configuration information according to the first embodiment. FIG. 4 is a diagram illustrating an example of a data structure of trajectory information according to the first embodiment. 1 is a flowchart illustrating an example of a process executed by a computer according to a first embodiment. 11 is a diagram illustrating an example of operation status information and work status information stored in work history information according to the first embodiment. FIG. 11 is a diagram illustrating an example of operation status information and work status information stored in work history information according to the first embodiment. FIG. FIG. 11 is a diagram illustrating an example of a method for generating estimated work state information by the computer of the first embodiment. FIG. 13 is a diagram illustrating an example of the configuration of a system according to a second embodiment. 13 is a flowchart illustrating an example of a process executed by a computer according to a second embodiment. FIG. 11 is a diagram illustrating an example of a data structure of noise analysis information generated by a computer according to a second embodiment. FIG. 11 is a diagram illustrating an example of a screen displayed by a computer according to a second embodiment. FIG. 11 is a diagram illustrating an example of a screen displayed by a computer according to a second embodiment. FIG. 11 is a diagram illustrating an example of noise removal by a computer according to a second embodiment.

The following describes an embodiment of the present invention with reference to the drawings. However, the present invention should not be interpreted as being limited to the description of the embodiment shown below. It will be easily understood by those skilled in the art that the specific configuration can be changed without departing from the concept or spirit of the present invention.

In the configuration of the invention described below, the same or similar configurations or functions are given the same reference symbols, and duplicate explanations are omitted.

The terms "first," "second," "third," and the like used in this specification are used to identify components and do not necessarily limit the number or order.

The position, size, shape, range, etc. of each component shown in the drawings, etc. may not represent the actual position, size, shape, range, etc., in order to facilitate understanding of the invention. Therefore, the present invention is not limited to the position, size, shape, range, etc. disclosed in the drawings, etc.

Figure 1 shows an example of the system configuration of Example 1.

The system is composed of a robot 100 and a computer 101. The robot 100 and the computer 101 are connected directly or via a network.

The robot 100 grasps an object (workpiece) and moves it from a starting point to an end point based on control information output from the computer 101. The robot 100 includes a group of working devices 110, a controller 111, and a measuring device 112.

The working device group 110 is a group of devices that realizes the grasping and movement of objects, such as hands, links, and drive motors.

The controller 111 controls the group of working devices 110 based on control information received from the computer 101. For example, the controller 111 moves the hand by driving drive motors that function as joints and connect links in accordance with the control information. The controller 111 outputs operating status information to the computer 101, including the angles, angular velocities, and angular accelerations of the joints, as well as the torque and current values of the drive motors.

The measuring device 112 measures values to grasp the state of an object due to work by the robot 100. The values output from the measuring device 112 are also referred to as work state information. The measuring device 112 is, for example, an acceleration sensor, a force sensor, a camera, a contact sensor, a current sensor, etc. The robot 100 may be equipped with multiple measuring devices 112 of different types for each measurement target. The present invention is not limited to the installation positions and number of measuring devices 112.

The robot 100 may transmit the operating status information and the work status information together as a single piece of information.

The computer 101 generates information on a trajectory (trajectory information), which is a moving path of the robot 100, and also generates control information based on the trajectory information, the operating status information, and the work status information. The control information includes, for example, the following values.
(1) Next target angle, angular velocity , and angular acceleration of the control axis; (2) Torque and drive current of the drive motor; (3) Target coordinates, moving velocity, and acceleration of the object.

The computer 101 includes a calculation device 120, a storage device 121, a communication device 122, an input device 123, and an output device 124. Each hardware element is connected via an internal bus.

The storage device 121 is a device that stores the programs and information executed by the computing device 120, and is, for example, a memory. The storage device 121 stores robot configuration information 140, equipment configuration information 141, trajectory information 142, model information 143, and work history information 144. The storage device 121 is also used as a work area.

The robot configuration information 140 is information about the configuration of the robot 100. The data structure of the robot configuration information 140 is explained using Figure 2.

The equipment configuration information 141 is information about the equipment on which the robot 100 performs work. The data structure of the equipment configuration information 141 will be explained using Figure 3.

Trajectory information 142 is information about the trajectory, which is the movement path of robot 100. The data structure of trajectory information 142 will be explained using Figure 4.

The model information 143 is information about a model (first model) that estimates an operation state and a model (second model) that generates control information. The first model and the second model are functions, tables, neural networks, or the like. In this embodiment, each model is a neural network. Each model is generated by machine learning using a simulator.

The work history information 144 is information that manages the operating status and work status history during work. Specifically, the work history information 144 accumulates operating status information and work status information.

The arithmetic device 120 is a device that controls the entire computer 101, and is, for example, a processor. The arithmetic device 120 executes a program stored in the memory device 121. The arithmetic device 120 executes processing according to the program, thereby operating as a functional unit (module) that realizes a specific function. In the following explanation, when a process is explained with the functional unit as the subject, it indicates that the arithmetic device 120 is executing a program that realizes the functional unit. In this embodiment, the arithmetic device 120 functions as a trajectory information generation unit 130, a task state estimation unit 131, and a control information generation unit 132.

The trajectory information generation unit 130 determines the trajectory of the hand based on input information such as the work content and the position of the object. The trajectory information generation unit 130 also determines the trajectory of the tool based on the robot configuration information 140, the equipment configuration information 141, and the trajectory of the hand. The trajectory information generation unit 130 generates trajectory information 142 that indicates the determined trajectory. Note that the method of determining the trajectory is a known technology, so a detailed explanation will be omitted.

The work state estimation unit 131 estimates the future work state based on the trajectory information 142, the operating state information and work state information accumulated in the work history information 144, and the first model.

The control information generation unit 132 generates control information based on the trajectory information 142, the operating status information and work status information accumulated in the work history information 144, the estimated work status, and the second model.

Regarding each functional unit of the computer 101, multiple functional units may be combined into one functional unit, or one functional unit may be divided into multiple functional units for each function.

The communication device 122 is a device for communicating with external devices, such as a NIC (Network Interface Card).

The input device 123 is a device for inputting data, commands, etc. to the computer 101, and is, for example, a keyboard, a mouse, a touch panel, etc.

The output device 124 is a device for outputting the calculation results of the calculator 101, and is, for example, a display, a projector, a printer, etc.

Figure 2 is a diagram showing an example of the data structure of robot configuration information 140 in Example 1.

The robot configuration information 140 stores entries including ID 201, classification 202, item 203, and content 204.

ID 201 is a field that stores the identification information of an entry. Classification 202 is a field that stores the classification of the elements that make up the robot 100. Item 203 is a field that stores the management items of the elements. Content 204 is a field that stores the contents of the management items. Files, numbers, character strings, etc. are stored in content 204.

For links, the shape of the links is managed. For joints that connect links, the connecting links, the joint type, and constraints on the movement of the joints are managed. Note that for joints, the items managed as constraints on the movement of the joints differ depending on the type of joint.

Figure 3 is a diagram showing an example of the data structure of the equipment configuration information 141 in Example 1.

The equipment configuration information 141 stores entries including an ID 301, equipment name 302, mounting target 303, relative position 304, and relative orientation 305.

ID 301 is a field that stores the identification information of an entry. Equipment name 302 is a field that stores the name of the equipment. Mounting target 303 is a field that stores the name of the object to be mounted on the equipment. Relative position 304 is a field that stores information (e.g., coordinates) that indicates the installation position relative to the equipment of the mounting target. Relative orientation 305 is a field that stores information (e.g., coordinates) that indicates the orientation relative to the equipment of the mounting target.

An entry with ID 301 of "0" indicates that the position and orientation of other equipment are determined based on assembly cell A. An entry with ID 301 of "1" stores the relative position and relative orientation of RoboA to be installed with respect to assembly cell A.

Figure 4 is a diagram showing an example of the data structure of trajectory information 142 in Example 1.

Trajectory information 142 stores a table 400 showing the hand trajectory and a table 410 showing the tool trajectory.

The table 400 stores entries including a via point 401, a position 402, an attitude 403, and a time 404.

Waypoint 401 is a field that stores identification information of waypoints on the trajectory. Position 402 is a group of fields that store values indicating the coordinates of the hand at the waypoint. Each field of position 402 stores a value in the Cartesian coordinate system. Orientation 403 is a group of fields that store values indicating the orientation of the hand at the waypoint. Each field of orientation 403 stores a value defined by a quaternion. Time 404 is a field that stores the time at which the hand, having started moving from the starting point, reaches the waypoint.

Table 410 stores entries including via points 411, attitudes 412, and time 413.

Waypoint 411 is the same field as waypoint 401. Posture 412 is a group of fields that store values indicating the posture of each joint at the waypoint. Each field of posture 412 stores the angle of the joint. Time 413 is the same field as Time 404.

The trajectory information 142 includes a set of table 400 and table 410 for each task. If the robot 100 body moves, the trajectory information 142 may include a table relating to the trajectory of the robot 100 body.

FIG. 5 is a flowchart illustrating an example of processing executed by the computer 101 of the first embodiment. FIGS. 6A and 6B are diagrams illustrating an example of operation status information and work status information stored in the work history information 144 of the first embodiment. FIG. 7 is a diagram illustrating an example of a method for generating estimated work status information by the computer 101 of the first embodiment. In the following description, it is assumed that the trajectory information 142 has already been generated.

The control information generator 132 starts a task loop process (step S101). The task loop process is repeatedly executed until a series of tasks, such as grasping an object and moving the object along a trajectory path, is completed.

The control information generator 132 acquires operating status information and work status information from the robot 100 (step S102) and stores the information in the work history information 144.

Operating status information is accumulated in the work history information 144 in a format as shown in FIG. 6A. One entry is operating status information acquired for each time step, which is the measurement period. Furthermore, working status information is accumulated in the work history information 144 in a format as shown in FIG. 6B. One entry is working status information acquired for each time step. Fx, Fy, Fz are force values in the X-axis, Y-axis, and Z-axis directions. Tx, Ty, Tz are torque values in the X-axis, Y-axis, and Z-axis directions. Ax, Ay, Az are accelerations in the X-axis, Y-axis, and Z-axis directions. Vx, Vy, Vz are velocities in the X-axis, Y-axis, and Z-axis directions.

The control information generating unit 132 determines whether processing is possible (step S103). Specifically, the control information generating unit 132 determines whether the number of pieces of operating status information and work status information required for processing have been accumulated. In this embodiment, it is determined whether five steps of operating status information and work status information have been accumulated. The number of pieces of operating status information and work status information is, for example, a value obtained by dividing the measurement frequency of the measuring device 112 by the analysis frequency resolution.

If processing is not possible, the control information generator 132 returns to step S102 and executes the same processing.

If processing is possible, the control information generation unit 132 generates estimated work state information by instructing the work state estimation unit 131 to estimate the work state (step S104).

For example, as shown in FIG. 7, the work state estimation unit 131 inputs five steps of operating state information and work state information, and two future steps of operating state information generated from trajectory information 142, into a neural network, which is the first model, to generate estimated work state information for the two future steps. Note that the items to be input into the first model, the number of operating state information and work state information to be input into the first model (length of the time series), and the number of estimated work state information to be generated can be set arbitrarily. Also, the structure of the neural network can be set arbitrarily.

The first model in this embodiment is assumed to incorporate the constraints contained in the robot configuration information 140.

The control information generation unit 132 generates control information by inputting the trajectory information 142, the operating status information and work status information accumulated in the work history information 144, and the estimated work status information into a neural network, which is the second model, and outputs the control information to the robot 100 (step S105).

If the work is not complete, the control information generating unit 132 returns to step S102 and executes the same process. If the work is complete, the control information generating unit 132 ends the loop process (step S106) and ends the series of processes.

At the start point of the trajectory, step S105 is performed without performing step S104. In this case, the control information generating unit 132 inputs, for example, the trajectory information 142 and the operating status information and work status information accumulated in the work history information 144 into the second model, and generates control information. Note that the control information for the start point may be generated by a different method.

According to the first embodiment, the computer 101 can generate control information that enables the robot to perform work safely and reliably by taking into account the current state of the object, the current state of the robot, and the future state of the object.

In the first embodiment, one computer 101 controls the robot 100, but a computer system including multiple computers 101 may perform similar control. In this case, the functional units may be distributed among the multiple computers 101.

In conventional technology, measurements taken by sensors are used to understand the state of the robot and object. The measurements contain noise caused by the environment, the robot, or the object, so it is necessary to remove the noise in order to control the robot with precision. In response to this, the technology described in Patent Document 2 is known.

In the method described in Patent Document 2, the robot must be operated in an unloaded state to perform sampling, which increases the amount of work required before the system is put into operation. In addition, in Patent Document 2, the value required for control is calculated by subtracting the sensor value in an unloaded state from the sensor value in a loaded state, but in the case of this method, the motion component is removed along with the noise.

In Example 2, a system is described that removes noise from measurement values without increasing the number of steps and uses the measurement values to control a robot. Below, Example 2 is described, focusing on the differences from Example 1.

Figure 8 shows an example of the system configuration for Example 2.

The system configuration of Example 2 is the same as that of Example 1. The configuration of the robot 100 of Example 2 is the same as that of Example 1. The hardware configuration of the computer 101 of Example 2 is the same as that of Example 1. Furthermore, the information held by the computer 101 of Example 2 is the same as that of Example 1. In Example 2, the functional configuration of the computer 101 is partially different from that of Example 1. The arithmetic device 120 of Example 2 further functions as a removal frequency determination unit 133 and a noise removal unit 134.

The removal frequency determination unit 133 determines the frequency to be removed as noise based on the shape of the trajectory. The noise removal unit 134 removes noise from the measurement values included in the work status information.

FIG. 9 is a flowchart illustrating an example of processing executed by the computer 101 of the second embodiment. FIG. 10 is a diagram illustrating an example of the data structure of noise analysis information generated by the computer 101 of the second embodiment. FIGS. 11A and 11B are diagrams illustrating an example of a screen displayed by the computer 101 of the second embodiment. FIG. 12 is a diagram illustrating an example of noise removal by the computer 101 of the second embodiment.

Before processing begins, the computer 101 displays a screen 1100 as shown in FIG. 11A via the output device 124. The screen 1100 includes display fields 1101, 1102, selection fields 1103, 1105, 1107, 1113, load buttons 1104, 1106, 1108, a removal pattern display field 1109, and an execute button 1114. Note that at the start of processing, the screen 1100 does not include the removal pattern display field 1109.

The selection field 1103 is a field for selecting the equipment to be used for the work. When the read button 1104 is operated, values related to the equipment specified in the selection field 1103 are read from the equipment configuration information 141.

The selection field 1105 is a field for selecting the task to be performed by the robot 100. When the load button 1106 is operated, the tables 400 and 410 corresponding to the task are read, and the trajectory is displayed in the display field 1101.

The selection field 1107 is a field for selecting the type of measurement value to be used to generate the control information. When the read button 1108 is operated, the value related to the sensor that measures the measurement value is read from the equipment configuration information 141.

The selection field 1113 is a field for selecting a first model. Note that the screen 1100 may also include a field for selecting a second model.

When the execute button 1114 is operated, the computer 101 starts the processing described below.

The control information generating unit 132 generates an elimination frequency pattern by instructing the elimination frequency determining unit 133 to generate an elimination frequency pattern (step S151). Specifically, the following process is executed.

(S151-1) The removal frequency determination unit 133 acquires the trajectory information 142, divides the trajectory into partial trajectories, and generates a set whose elements are the divided partial trajectories. The removal frequency determination unit 133 generates multiple sets by changing the division method. The trajectory itself is also generated as a set. Furthermore, the removal frequency determination unit 133 generates a family whose elements are the set. The removal frequency determination unit 133 assigns an identification number as identification information for the family.

(S151-2) The removal frequency determination unit 133 selects one set from the family.

(S151-3) The removal frequency determination unit 133 selects a partial orbit from the selected set.

(S151-4) The elimination frequency determination unit 133 selects the coordinate axis to be analyzed. At this time, the elimination frequency determination unit 133 adds an entry to the noise analysis information 1000.

The noise analysis information 1000 stores entries each consisting of an ID 1001, a partial route ID 1002, a coordinate axis 1003, and a frequency 1004. The ID 1001 is a field that stores identification information of an entry (family). The partial route ID 1002 is a field that stores identification information of a partial route. The partial route ID 1002 stores a pair of a waypoint that is the start point of the partial route and a waypoint that is the end point of the partial route. The coordinate axis 1003 is a field that stores the coordinate axis to be analyzed. The frequency 1004 is a group of fields that stores the spectral values of frequency components. The number of frequency components can be set arbitrarily. The sum of the spectral values of each frequency component is 1.

The removal frequency determination unit 133 sets the family identification information to the ID 1001 of the added entry, sets the partial path identification information to the partial path ID 1002, and sets the coordinate axis to the coordinate axis 1003.

(S151-5) The elimination frequency determination unit 133 converts the shape of the partial trajectory on the selected coordinate axis into frequency components using a known technique such as FFT (Fast Fourier Transformation). The elimination frequency determination unit 133 sets the spectrum value of the frequency components to the frequency 1004 of the entry added to the noise analysis information 1000.

(S151-6) The removal frequency determination unit 133 determines whether or not processing has been completed for all of the X-axis, Y-axis, and Z-axis coordinate axes. If processing has not been completed for all of the X-axis, Y-axis, and Z-axis coordinate axes, the removal frequency determination unit 133 returns to S151-4 and executes the same processing.

(S151-7) When processing has been completed for all coordinate axes, the X-axis, the Y-axis, and the Z-axis, the elimination frequency determination unit 133 determines whether processing has been completed for all partial orbits of the selected set. If processing has not been completed for all partial orbits of the selected set, the elimination frequency determination unit 133 returns to S151-3 and executes the same processing.

(S151-8) When processing has been completed for all partial trajectories of the selected set, the removal frequency determination unit 133 determines the frequency to be removed for each combination of partial trajectories and coordinate axes. In this embodiment, the frequency corresponding to a spectrum value greater than the threshold is determined as the removal frequency. The removal frequency determination unit 133 saves information on the removal frequency for each combination of partial trajectories and coordinate axes as a removal pattern in the work area. Note that the removal pattern is assigned family identification information.

(S151-9) The removal frequency determination unit 133 judges whether or not processing has been completed for all sets. If processing has not been completed for all sets, the removal frequency determination unit 133 returns to S151-2 and executes the same processing. If processing has been completed for all sets, the removal frequency determination unit 133 displays information on the removal pattern in the removal pattern display field 1109. The removal pattern display field 1109 displays the removal pattern in a table format. The table stores entries including ID 1110, removal pattern 1111, and selection 1112. ID 1110 is a field that displays identification information of the removal pattern. Removal pattern 1111 is a field that displays the removal pattern. Selection 1112 is a field for selecting a removal pattern. The user selects the removal pattern to be used by inputting a check in selection 1112. The removal frequency determination unit 133 displays the removal pattern superimposed on the trajectory in the display field 1102.

If the control information generator 132 receives a selection of a removal pattern from the user, it ends the processing of step S151.

The processing from step S101 to step S103 is the same as in Example 1. If it is determined in step S103 that the processing is possible, the control information generating unit 132 instructs the noise removing unit 134 to remove noise, thereby removing noise from the work status information (step S152). Specifically, the following processing is executed.

(S152-1) The noise removal unit 134 reads out the removal pattern selected by the user.

(S152-2) The noise removal unit 134 identifies the trajectory of each time step based on the trajectory information 142 and the operation status information, obtains the frequency corresponding to the identified trajectory from the removal pattern, and subtracts the frequency from the operation status information. As a result, for example, noise is removed as shown in FIG. 12.

The processing from step S104 to step S106 is the same as in Example 1. However, steps S104 and S105 are different from Example 1 in that noise-removed work status information is used.

During work, the control information generator 132 may display display fields 1121, 1122, 1123, and 1124 showing the noise removal results and estimated work state information on the left side of the screen 1100 as shown in FIG. 11B. Display field 1121 is the same as display field 1102. Display field 1122 is a field that displays the measurement value before noise is removed. Display field 1123 is a field that displays the measurement value after noise is removed. Display field 1124 is a field that displays the estimated work state information. The second model outputs control information that does not exceed the threshold. Note that in FIG. 11B, the execute button 1114 has been changed to a stop button 1115.

According to the second embodiment, noise can be removed from the measurement values without increasing the number of steps and while leaving the movement components intact.

In the second embodiment, one computer 101 controls the robot 100, but a computer system including multiple computers 101 may perform similar control. In this case, the functional units may be distributed among the multiple computers 101.

The present invention is not limited to the above-described embodiments, but includes various modified examples. For example, the above-described embodiments are provided to explain the present invention in detail, and are not necessarily limited to those including all of the described configurations. In addition, it is possible to add, delete, or replace part of the configuration of each embodiment with another configuration.

The above-mentioned configurations, functions, processing units, processing means, etc. may be realized in part or in whole by hardware, for example by designing them as integrated circuits. The present invention can also be realized by software program code that realizes the functions of the embodiments. In this case, a storage medium on which the program code is recorded is provided to a computer, and a processor included in the computer reads the program code stored in the storage medium. In this case, the program code itself read from the storage medium realizes the functions of the above-mentioned embodiments, and the program code itself and the storage medium on which it is stored constitute the present invention. Examples of storage media for supplying such program code include flexible disks, CD-ROMs, DVD-ROMs, hard disks, SSDs (Solid State Drives), optical disks, magneto-optical disks, CD-Rs, magnetic tapes, non-volatile memory cards, and ROMs.

In addition, the program code that realizes the functions described in this embodiment can be implemented in a wide range of program or script languages, such as assembler, C/C++, perl, Shell, PHP, Python, Java (registered trademark), etc.

Furthermore, the program code of the software that realizes the functions of the embodiment may be distributed over a network and stored in a storage means such as a computer's hard disk or memory, or in a storage medium such as a CD-RW or CD-R, and the processor of the computer may read and execute the program code stored in the storage means or storage medium.

In the above examples, the control lines and information lines are those that are considered necessary for the explanation, and not all control lines and information lines in the product are necessarily shown. All components may be interconnected.

REFERENCE SIGNS LIST 100 Robot 101 Computer 110 Working device group 111 Controller 112 Measuring device 120 Calculating device 121 Storage device 122 Communication device 123 Input device 124 Output device 130 Trajectory information generating unit 131 Working state estimating unit 132 Control information generating unit 133 Removal frequency determining unit 134 Noise removing unit 140 Robot configuration information 141 Equipment configuration information 142 Trajectory information 143 Model information 144 Work history information 1000 Noise analysis information 1100 Screen

Claims (15)

A computer that controls a robot that performs a task including grasping and moving an object,
a computing device, a storage device connected to the computing device, and an interface connected to the computing device;
the storage device holds trajectory information regarding a trajectory of the robot when gripping and moving the object in a task performed by the robot;
The computing device includes:
Acquiring first operating status information including a value indicating an operating status of the robot during work and work status information including a value for grasping a status of the object grasped by the robot;
generating second operating status information including a value indicating a future operating status of the robot during work, the second operating status information being generated based on the trajectory information, and based on the first operating status information and the work status information , generating estimated work status information including a value for grasping a future state of the object to be grasped by the robot;
A computer that generates control information for controlling the robot based on the trajectory information, the first operating status information, the work status information, and the estimated work status information. 2. The computer of claim 1,
The storage device is a computer characterized by storing a first model that accepts the first operating status information , the second operating status information, and the work status information as inputs and outputs the estimated work status information, and a second model that accepts the trajectory information, the first operating status information, the work status information, and the estimated work status information as inputs and outputs the control information. 3. The computer of claim 2,
The computer, wherein the first model and the second model are neural networks generated by machine learning. 2. The computer of claim 1,
the work status information includes a measurement value acquired from a measurement device that is installed on the robot and measures a value for grasping a status of the object grasped by the robot,
The computing device includes:
Calculating a removal frequency according to a shape of the trajectory based on the trajectory information;
A computer that removes noise from the measurement value included in the work status information based on the removal frequency. 5. The computer of claim 4,
The arithmetic unit is a computer that calculates the removal frequency according to a shape of the trajectory for each coordinate axis. 5. The computer of claim 4,
The computing device includes:
Dividing the trajectory into a plurality of partial paths;
A computer that calculates the removal frequency for each of the partial paths. A method for controlling a robot that performs a task including grasping and moving an object, the method comprising the steps of:
the computer includes a processor, a storage device connected to the processor, and an interface connected to the processor;
the storage device holds trajectory information regarding a trajectory of the robot when gripping and moving the object in a task performed by the robot;
The method for controlling a robot includes the steps of:
A first step in which the arithmetic device acquires first operating status information including a value indicating an operating status of the robot during work, and work status information including a value for grasping a status of the object grasped by the robot;
a second step in which the arithmetic device generates second operating status information including a value indicating a future operating status of the robot during work, the second operating status information being generated based on the trajectory information , and estimated work status information including a value for grasping a future state of the object to be grasped by the robot, based on the first operating status information and the work status information;
and a third step in which the calculation device generates control information for controlling the robot based on the trajectory information, the first operating status information, the work status information, and the estimated work status information. A method for controlling a robot according to claim 7, comprising the steps of:
a first model that accepts the first operating status information , the second operating status information, and the work status information as inputs and outputs the estimated work status information, and a second model that accepts the trajectory information, the first operating status information, the work status information, and the estimated work status information as inputs and outputs the control information, wherein the storage device stores therein a first model that accepts the first operating status information, the second operating status information, and the work status information as inputs and outputs the control information. A method for controlling a robot according to claim 8, comprising the steps of:
A method for controlling a robot, wherein the first model and the second model are neural networks generated by machine learning. A method for controlling a robot according to claim 7, comprising the steps of:
the work status information includes a measurement value acquired from a measurement device that is installed on the robot and measures a value for grasping a status of the object,
The first step includes:
a fourth step in which the calculation device calculates a removal frequency according to a shape of the trajectory based on the trajectory information;
and a fifth step in which the calculation device removes noise from the measurement value included in the work status information based on the removal frequency. A method for controlling a robot according to claim 10, comprising the steps of:
The robot control method, wherein the fourth step includes a step in which the arithmetic device calculates the removal frequency according to a shape of the trajectory for each coordinate axis. A method for controlling a robot according to claim 10, comprising the steps of:
The fourth step includes:
The computing device divides the trajectory into a plurality of partial paths;
the calculation device calculating the removal frequency for each of the partial paths. A computer system for controlling a robot that performs a task including grasping and moving an object, comprising:
A plurality of computers each having a computing device, a storage device connected to the computing device, and an interface connected to the computing device;
managing trajectory information regarding a trajectory of the robot when gripping and moving the object in a task of the robot;
The computer includes:
Acquiring first operating status information including a value indicating an operating status of the robot during work and work status information including a value for grasping a status of the object grasped by the robot;
generating second operating status information including a value indicating a future operating status of the robot during work, the second operating status information being generated based on the trajectory information, and based on the first operating status information and the work status information , generating estimated work status information including a value for grasping a future state of the object to be grasped by the robot;
A computer system comprising: a computer that generates control information for controlling the robot based on the trajectory information, the first operating status information, the work status information, and the estimated work status information. 14. The computer system of claim 13,
A computer system characterized by managing a first model that accepts the first operating status information , the second operating status information, and the work status information as inputs and outputs the estimated work status information, and a second model that accepts the trajectory information, the first operating status information, the work status information, and the estimated work status information as inputs and outputs the control information. 14. The computer system of claim 13,
the work status information includes a measurement value acquired from a measurement device that is installed on the robot and measures a value for grasping a status of the object grasped by the robot,
The computer includes:
Calculating a removal frequency according to a shape of the trajectory based on the trajectory information;
A computer system which removes noise from the measurement value included in the work status information based on the removal frequency.

Images